Daniil Ryabko

Publication Activity (10 Years)

Years Active: 2004-2020
Publications (10 Years): 17

Top Topics

Reinforcement Learning

Multi Armed Bandit

Binary Classification

Top Venues

Publications

Daniil Ryabko
Time-Series Information and Unsupervised Learning of Representations. IEEE Trans. Inf. Theory 66 (3) (2020)
Daniil Ryabko
Universal time-series forecasting with mixture predictors. CoRR (2020)
Azadeh Khaleghi, Daniil Ryabko
Clustering piecewise stationary processes. ISIT (2020)
Azadeh Khaleghi, Daniil Ryabko
Clustering piecewise stationary processes. CoRR (2019)
Daniil Ryabko
Asymptotic nonparametric statistical analysis of stationary time series. CoRR (2019)
Daniil Ryabko
On Asymptotic and Finite-Time Optimality of Bayesian Predictors. J. Mach. Learn. Res. 20 (2019)
Daniil Ryabko
Finite-time optimality of Bayesian predictors. CoRR (2018)
Daniil Ryabko
Independence clustering (without a matrix). CoRR (2017)
Daniil Ryabko
Universality of Bayesian mixture predictors. ALT (2017)
Daniil Ryabko
Hypotheses testing on infinite random graphs. CoRR (2017)
Daniil Ryabko
Independence clustering (without a matrix). NIPS (2017)
Daniil Ryabko
Hypotheses testing on infinite random graphs. ALT (2017)
Azadeh Khaleghi, Daniil Ryabko
Nonparametric multiple change point estimation in highly dependent time series. Theor. Comput. Sci. 620 (2016)
Daniil Ryabko
Universality of Baysian mixture predictors. CoRR (2016)
Daniil Ryabko
Things Bayes can't do. CoRR (2016)
Daniil Ryabko
Things Bayes Can't Do. ALT (2016)
Azadeh Khaleghi, Daniil Ryabko, Jérémie Mary, Philippe Preux
Consistent Algorithms for Clustering Time Series. J. Mach. Learn. Res. 17 (2016)
Daniil Ryabko, Boris Ryabko
Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible. ISIT (2015)
Daniil Ryabko, Boris Ryabko
Predicting the outcomes of every process for which an asymptotically accurate stationary predictor exists is impossible. CoRR (2015)
Amir Sani, Alessandro Lazaric, Daniil Ryabko
The replacement bootstrap for dependent data. ISIT (2015)
K. Lakshmanan, Ronald Ortner, Daniil Ryabko
Improved Regret Bounds for Undiscounted Continuous Reinforcement Learning. ICML (2015)
Ronald Ortner, Odalric-Ambrym Maillard, Daniil Ryabko
Selecting Near-Optimal Approximate State Representations in Reinforcement Learning. ALT (2014)
Ronald Ortner, Odalric-Ambrym Maillard, Daniil Ryabko
Selecting Near-Optimal Approximate State Representations in Reinforcement Learning. CoRR (2014)
Ronald Ortner, Daniil Ryabko, Peter Auer, Rémi Munos
Regret bounds for restless Markov bandits. Theor. Comput. Sci. 558 (2014)
Azadeh Khaleghi, Daniil Ryabko
Asymptotically consistent estimation of the number of change points in highly dependent time series. ICML (2014)
Odalric-Ambrym Maillard, Phuong Nguyen, Ronald Ortner, Daniil Ryabko
Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning CoRR (2013)
Odalric-Ambrym Maillard, Rémi Munos, Daniil Ryabko
Selecting the State-Representation in Reinforcement Learning CoRR (2013)
Azadeh Khaleghi, Daniil Ryabko
Nonparametric Multiple Change Point Estimation in Highly Dependent Time Series. ALT (2013)
Phuong Nguyen, Odalric-Ambrym Maillard, Daniil Ryabko, Ronald Ortner
Competing with an Infinite Set of Models in Reinforcement Learning. AISTATS (2013)
Daniil Ryabko
Unsupervised Model-Free Representation Learning. ALT (2013)
Daniil Ryabko
Unsupervised model-free representation learning CoRR (2013)
Odalric-Ambrym Maillard, Phuong Nguyen, Ronald Ortner, Daniil Ryabko
Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning. ICML (1) (2013)
Daniil Ryabko
Time-series information and learning. ISIT (2013)
Azadeh Khaleghi, Daniil Ryabko
A consistent clustering-based approach to estimating the number of change-points in highly dependent time-series CoRR (2013)
Daniil Ryabko, Jérémie Mary
A binary-classification-based metric between time-series distributions and its use in statistical and learning problems. J. Mach. Learn. Res. 14 (1) (2013)
Ronald Ortner, Daniil Ryabko
Online Regret Bounds for Undiscounted Continuous Reinforcement Learning CoRR (2013)
Ronald Ortner, Daniil Ryabko, Peter Auer, Rémi Munos
Regret Bounds for Restless Markov Bandits. ALT (2012)
Azadeh Khaleghi, Daniil Ryabko
Multiple Change-Point Estimation in Stationary Ergodic Time-Series CoRR (2012)
Daniil Ryabko, Jérémie Mary
Reducing statistical time-series problems to binary classification. NIPS (2012)
Azadeh Khaleghi, Daniil Ryabko
Locating Changes in Highly Dependent Data with Unknown Number of Change Points. NIPS (2012)
Daniil Ryabko, Jérémie Mary
Reducing statistical time-series problems to binary classification CoRR (2012)
Ronald Ortner, Daniil Ryabko
Online Regret Bounds for Undiscounted Continuous Reinforcement Learning. NIPS (2012)
Ronald Ortner, Daniil Ryabko, Peter Auer, Rémi Munos
Regret Bounds for Restless Markov Bandits CoRR (2012)
Azadeh Khaleghi, Daniil Ryabko, Jérémie Mary, Philippe Preux
Online Clustering of Processes. AISTATS (2012)
Boris Ryabko, Daniil Ryabko
Confidence sets in time-series filtering. ISIT (2011)
Daniil Ryabko
On the Relation between Realizable and Nonrealizable Cases of the Sequence Prediction Problem. J. Mach. Learn. Res. 12 (2011)
Boris Ryabko, Daniil Ryabko
Constructing perfect steganographic systems. Inf. Comput. 209 (9) (2011)
Odalric-Ambrym Maillard, Rémi Munos, Daniil Ryabko
Selecting the State-Representation in Reinforcement Learning. NIPS (2011)
Daniil Ryabko
Clustering processes. ICML (2010)
Daniil Ryabko
Sequence prediction in realizable and non-realizable cases CoRR (2010)
Daniil Ryabko
Clustering processes CoRR (2010)
Boris Ryabko, Daniil Ryabko
Confidence Sets in Time--Series Filtering CoRR (2010)
Daniil Ryabko
On Finding Predictors for Arbitrary Families of Processes. J. Mach. Learn. Res. 11 (2010)
Daniil Ryabko
Clustering processes CoRR (2010)
Daniil Ryabko
Sequence Prediction in Realizable and Non-realizable Cases. COLT (2010)
Daniil Ryabko, Boris Ryabko
Nonparametric statistical inference for ergodic processes. IEEE Trans. Inf. Theory 56 (3) (2010)
Daniil Ryabko
Characterizing predictable classes of processes CoRR (2009)
Daniil Ryabko
On Finding Predictors for Arbitrary Families of Processes CoRR (2009)
Daniil Ryabko
A criterion for hypothesis testing for stationary processes CoRR (2009)
Boris Ryabko, Daniil Ryabko
Using Kolmogorov Complexity for Understanding Some Limitations on Steganography CoRR (2009)
B. Ya. Ryabko, Daniil Ryabko
Asymptotically optimal perfect steganographic systems. Probl. Inf. Transm. 45 (2) (2009)
Jean-Yves Audibert, Peter Auer, Alessandro Lazaric, Rémi Munos, Daniil Ryabko, Csaba Szepesvári
Workshop summary: On-line learning with limited feedback. ICML (2009)
Boris Ryabko, Daniil Ryabko
Using Kolmogorov complexity for understanding some limitations on steganography. ISIT (2009)
Daniil Ryabko, Jürgen Schmidhuber
Using data compressors to construct order tests for homogeneity and component independence. Appl. Math. Lett. 22 (7) (2009)
Daniil Ryabko
Characterizing predictable classes of processes. UAI (2009)
Daniil Ryabko
An impossibility result for process discrimination. ISIT (2009)
Daniil Ryabko, Boris Ryabko
On hypotheses testing for ergodic processes. ITW (2008)
Daniil Ryabko, Marcus Hutter
On the possibility of learning in reactive environments with arbitrary dependence. Theor. Comput. Sci. 405 (3) (2008)
Daniil Ryabko, Boris Ryabko
Testing Statistical Hypotheses About Ergodic Processes CoRR (2008)
Daniil Ryabko
Some Sufficient Conditions on an Arbitrary Class of Stochastic Processes for the Existence of a Predictor. ALT (2008)
Daniil Ryabko
An impossibility result for process discrimination CoRR (2008)
Daniil Ryabko, Marcus Hutter
On the Possibility of Learning in Reactive Environments with Arbitrary Dependence CoRR (2008)
Boris Ryabko, Daniil Ryabko
Constructing Perfect Steganographic Systems CoRR (2008)
Daniil Ryabko, Marcus Hutter
Predicting non-stationary processes. Appl. Math. Lett. 21 (5) (2008)
Daniil Ryabko
Testing Component Independence Using Data Compressors. ICANN (2) (2007)
Daniil Ryabko, Jürgen Schmidhuber
Using Data Compressors to Construct Rank Tests CoRR (2007)
Boris Ryabko, Daniil Ryabko
Information-Theoretic Approach to Steganographic Systems. ISIT (2007)
Daniil Ryabko, Marcus Hutter
On Sequence Prediction for Arbitrary Measures. ISIT (2007)
Daniil Ryabko
Sample Complexity for Computational Classification Problems. Algorithmica 49 (1) (2007)
Daniil Ryabko, Marcus Hutter
Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence CoRR (2006)
Daniil Ryabko
Pattern Recognition for Conditionally Independent Data. J. Mach. Learn. Res. 7 (2006)
Daniil Ryabko, Marcus Hutter
Sequence prediction for non-stationary processes. Combinatorial and Algorithmic Foundations of Pattern and Association Discovery (2006)
Daniil Ryabko, Marcus Hutter
Learning in Reactive Environments with Arbitrary Dependence. Kolmogorov Complexity and Applications (2006)
Boris Ryabko, Daniil Ryabko
Provably Secure Universal Steganographic Systems CoRR (2006)
Daniil Ryabko, Marcus Hutter
Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence. ALT (2006)
Boris Ryabko, Daniil Ryabko
Provably Secure Universal Steganographic Systems. IACR Cryptol. ePrint Arch. 2006 (2006)
Daniil Ryabko, Marcus Hutter
On Sequence Prediction for Arbitrary Measures CoRR (2006)
Daniil Ryabko
On Computability of Pattern Recognition Problems. ALT (2005)
Daniil Ryabko
On sample complexity for computational pattern recognition CoRR (2005)
Daniil Ryabko
Pattern Recognition for Conditionally Independent Data CoRR (2005)
Daniil Ryabko
Application of Classical Nonparametric Predictors to Learning Conditionally I.I.D. Data. ALT (2004)
Daniil Ryabko
Online learning of conditionally I.I.D. data. ICML (2004)